Papers › An Empirical Study of Scaling Law for OCR
An Empirical Study of Scaling Law for OCR
Miao Rang, Zhenni Bi, Chuanjian Liu, Yunhe Wang, Kai Han
The laws of model size, data volume, computation and model performance have been extensively studied in the field of Natural Language Processing (NLP). However, the scaling laws in Optical Character Recognition (OCR) have not yet been investigated. To address this, we conducted comprehensive studies that involved examining the correlation between performance and the scale of models, data volume and computation in the field of text recognition.Conclusively, the study demonstrates smooth power laws between performance and model size, as well as training data volume, when other influencing factors are held constant. Additionally, we have constructed a large-scale dataset called REBU-Syn, which comprises 6 million real samples and 18 million synthetic samples. Based on our scaling law and new dataset, we have successfully trained a scene text recognition model, achieving a new state-ofthe-art on 6 common test benchmarks with a top-1 average accuracy of 97.42%. The models and dataset are publicly available at https://github.com/large-ocr-model/large-ocr-model.github.io.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Scene Text Recognition | CUTE80 | CLIP4STR-B* | Accuracy | 99.65 | #3 of 18 | Archive leaderboard | report |
| Scene Text Recognition | ICDAR2013 | CLIP4STR-L* | Accuracy | 99.42 | #1 of 38 | Archive leaderboard | report |
| Scene Text Recognition | ICDAR2015 | CLIP4STR-L* | Accuracy | 92.6 | #2 of 27 | Archive leaderboard | report |
| Scene Text Recognition | SVT | CLIP4STR-B* | Accuracy | 98.76 | #3 of 37 | Archive leaderboard | report |
| Scene Text Recognition | SVTP | CLIP4STR-L* | Accuracy | 98.13 | #3 of 17 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections